A Field Demonstration of an Instrument Performing Automatic Classification of Geologic Surfaces

This work presents a method to automate simple aspects of geologic image analysis during space exploration. Automated image analysis onboard the spacecraft can make operations more efficient by generating compressed maps of long traverses for summary downlink. It can also enable immediate automatic responses to science targets of opportunity, improving the quality of targeted measurements collected with each command cycle. In addition, automated analyses on Earth can process large image catalogs, such as the growing database of Mars surface images, permitting more timely and quantitative summaries that inform tactical mission operations. We present TextureCam, a new instrument incorporating real time image analysis to produce texture-sensitive classifications of geologic surfaces in mesoscale scenes. A series of tests at the Cima Volcanic Fields in the Mojave Desert, California demonstrate mesoscale surficial mapping at two distinct sites of